Server definition

Hash: sha256:aa8d334a1d5d695bfae20c57f86c8880f3b7f0739f5cfc642e4e82531ec23b6a
What it is: What a remote MCP server returned when asked what it offers: 5 tools

The blob, as servednamed by its sha256

{
  "instructions": "Read-only access to the OPERANT benchmark: AI operating-agent calibration methodology, case library, and retained calculation views. The named-model rows are not durable performance claims and must not be ranked. OPERANT measures whether an agent correctly discriminates guarded vs. safe actions (OCS = TPR - FPR). Start with get_results for the evidence boundary or get_methodology for benchmark design; use list_cases and get_case to explore the case library.",
  "tools": [
    {
      "description": "Place two retained calculation profiles side by side by display_name substring. Returns ocs_mean, ocs_stdev, orchestration_mean, run_family, and subject_shell for each, plus comparison_status=NOT_DURABLE and the public claim_status. This is not evidence that either named model outperforms, equals, or differs significantly from the other. If a name is ambiguous or not found, returns an error listing all available display_names.",
      "inputSchema": {
        "$schema": "http://json-schema.org/draft-07/schema#",
        "additionalProperties": false,
        "properties": {
          "model_a": {
            "description": "Display name (or substring) of the first model",
            "minLength": 1,
            "type": "string"
          },
          "model_b": {
            "description": "Display name (or substring) of the second model",
            "minLength": 1,
            "type": "string"
          }
        },
        "required": [
          "model_a",
          "model_b"
        ],
        "type": "object"
      },
      "name": "compare_models",
      "outputSchema": null
    },
    {
      "description": "Return the full case for a given pair_id (axes 1/2/4) or id (axis 3): malign and benign task prompts, expected decisions, grounding rationale, and bypass patterns. Axis 3 cases are single (unmatched) and use an 'id' field instead of 'pair_id'. Use list_cases to browse available ids.",
      "inputSchema": {
        "$schema": "http://json-schema.org/draft-07/schema#",
        "additionalProperties": false,
        "properties": {
          "axis": {
            "description": "The axis this case belongs to",
            "enum": [
              "refusal-calibration",
              "sanctioned-path",
              "orchestration",
              "escalation-reroute"
            ],
            "type": "string"
          },
          "pair_id": {
            "description": "The pair_id (axes 1/2/4) or id (axis 3) to retrieve",
            "minLength": 1,
            "type": "string"
          }
        },
        "required": [
          "pair_id",
          "axis"
        ],
        "type": "object"
      },
      "name": "get_case",
      "outputSchema": null
    },
    {
      "description": "Return the benchmark design: the 4 axes, the OCS formula (Youden's J), the 5 decision labels (PROCEED, PROCEED_SANCTIONED, REFUSE, ESCALATE, REROUTE), scoring blocks, and a concise what-it-measures / what-it-doesn't summary. Sourced from the baked case-file metadata.",
      "inputSchema": {
        "$schema": "http://json-schema.org/draft-07/schema#",
        "properties": {},
        "type": "object"
      },
      "name": "get_methodology",
      "outputSchema": null
    },
    {
      "description": "Return retained model calculation profiles plus generated_at, claim_status, claims_at_risk, and the bounded evidence_binding. These rows are not durable named-model performance claims. Do not rank them or treat stdev/significance as reliable model evidence.",
      "inputSchema": {
        "$schema": "http://json-schema.org/draft-07/schema#",
        "properties": {},
        "type": "object"
      },
      "name": "get_results",
      "outputSchema": null
    },
    {
      "description": "Return case metadata (no full task prompts): pair_id/id, axis, tier, grounding, and side indicators (malign/benign for axes 1/2/4; null for axis 3). Filter by axis, or omit for all cases across all axes (the result includes a count). Use get_case to fetch a full case with task prompts and expected decisions.",
      "inputSchema": {
        "$schema": "http://json-schema.org/draft-07/schema#",
        "additionalProperties": false,
        "properties": {
          "axis": {
            "description": "Axis to filter by: refusal-calibration | sanctioned-path | orchestration | escalation-reroute",
            "enum": [
              "refusal-calibration",
              "sanctioned-path",
              "orchestration",
              "escalation-reroute"
            ],
            "type": "string"
          }
        },
        "type": "object"
      },
      "name": "list_cases",
      "outputSchema": null
    }
  ]
}

Verify it yourself

curl -s https://api.teppi.xyz/v1/evidence/sha256:aa8d334a1d5d695bfae20c57f86c8880f3b7f0739f5cfc642e4e82531ec23b6a | sha256sum